Disentangled Fine-Grained Prototype Learning for Incomplete Image-Tabular Classification

Researchers have developed DFPL, a framework for incomplete image-tabular classification that addresses the missing-modality problem through fine-grained prototype learning. The method introduces Shared-Specific Prototype Modeling and Prototype-guided Fine-grained Alignment to capture cross-modal consistency at the prototype level, overcoming limitations of existing approaches that rely on coarse global features. Experiments on three benchmarks show DFPL outperforms prior methods across various missing-modality scenarios.

arXiv:2606.05455v1 Announce Type: new Abstract: The missing-modality problem poses a significant challenge in image-tabular multimodal learning across a wide range of multimedia applications, including product understanding, recommendation systems, and medical diagnosis. This challenge is particularly pronounced when the two modalities are highly heterogeneous, as images and tabular attributes differ substantially in their semantic granularity and data distributions. Existing methods learn modality-invariant representations through disentanglement and alignment over global token-averaged features, capturing only coarse cross-modal consistency and overlooking fine-grained semantic and distributional misalignment, which hampers the exploitation of complementary cues under missing modalities. To address this, we propose DFPL, a novel framework for fine-grained prototype learning. Specifically, Shared-Specific Prototype Modeling SSPM extracts compact and diverse shared and modality-specific prototypes, and further performs prototype-level disentanglement to suppress redundant intra-modality correlations. Additionally, we propose a Prototype-guided Fine-grained Alignment PFA module that jointly enforces prototype-level distribution matching and prototype-to-class semantic alignment within a unified prototype space, thereby preserving both fine-grained distributional and semantic consistency across modalities. We further introduce a Class-aware Multi-scale Aggregation CMA module to adaptively aggregate shared semantics and modality-specific characteristics from global and prototype levels for robust predictions. Extensive experiments on three diverse image-tabular benchmarks demonstrate the superiority of our method compared to the previous approaches under various missing-modality settings. Code will be made publicly available.